An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the no...An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.展开更多
To avoid the exhaustive search, we propose a fast user selection algorithm for Signal-to-Interference-plus-Noise-Ratio (SINR)-based multiuser Multiple-Input Multiple-Output (MIMO) systems with Alamouti Space-Time Bloc...To avoid the exhaustive search, we propose a fast user selection algorithm for Signal-to-Interference-plus-Noise-Ratio (SINR)-based multiuser Multiple-Input Multiple-Output (MIMO) systems with Alamouti Space-Time Block Code (STBC) transmit scheme. A locally optimal selection criterion is proposed at first. Then, the incremental selection approach is applied, which selects one among the residual available users to maximize the minimum user SINR step by step. Simulation results show that the fast algorithm gains over 90% of the diversity benefit achieved by the exhaustive search selection, and that the fast algorithm has much lower computational burden than the exhaustive search one, for the scenario where the number of all the available users is much greater than that of the selected users.展开更多
基金Supported by the National Natural Science Foundation of China (60575009, 60574036)
文摘An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.
文摘To avoid the exhaustive search, we propose a fast user selection algorithm for Signal-to-Interference-plus-Noise-Ratio (SINR)-based multiuser Multiple-Input Multiple-Output (MIMO) systems with Alamouti Space-Time Block Code (STBC) transmit scheme. A locally optimal selection criterion is proposed at first. Then, the incremental selection approach is applied, which selects one among the residual available users to maximize the minimum user SINR step by step. Simulation results show that the fast algorithm gains over 90% of the diversity benefit achieved by the exhaustive search selection, and that the fast algorithm has much lower computational burden than the exhaustive search one, for the scenario where the number of all the available users is much greater than that of the selected users.
